Add S3/MinIO storage backend tests for storage.py

21 test cases covering:
- S3StorageBackend: read, write, exists, path_for with mocked boto3
- Error handling: NoSuchKey exception, generic 404, non-404 re-raise
- Bucket auto-creation on init and graceful handling of creation failure
- Constructor credential/endpoint passthrough
- LocalStorageBackend: round-trip read/write, missing file, empty file
- get_storage_backend() factory: local/s3 selection, case-insensitivity

Closes leeworks-agents/SPARC#1660

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

.gitea/workflows/build.yaml

@@ -28,10 +28,10 @@ jobs:
         run: |
           pip3 install -r requirements.txt ruff
 
-#      - name: Run ruff linter
-#        shell: sh
-#        run: |
-#          ruff check SPARC/ tests/
+      - name: Run ruff linter
+        shell: sh
+        run: |
+          ruff check SPARC/ tests/
 
       - name: Install Node.js and check TypeScript types
         shell: sh
@@ -47,16 +47,17 @@ jobs:
           fi
           npx tsc --noEmit
 
-#      - name: Run pytest
-#        shell: sh
-#        env:
-#          DATABASE_URL: "sqlite://"
-#          API_KEY: "test-key"
-#          OPENROUTER_API_KEY: "test-key"
-#          JWT_SECRET: "test-secret-for-ci"
-#          APP_ENV: "development"
-#        run: |
-#          python3 -m pytest tests/ -v --tb=short -x
+      - name: Run pytest
+        shell: sh
+        env:
+          DATABASE_URL: "sqlite://"
+          API_KEY: "test-key"
+          OPENROUTER_API_KEY: "test-key"
+          JWT_SECRET: "test-secret-for-ci"
+          APP_ENV: "development"
+        run: |
+          pip3 install pytest
+          python3 -m pytest tests/ -v --tb=short -x
 
   build-api:
     needs: test

SPARC/analyzer.py

@@ -10,13 +10,13 @@ from concurrent.futures import ThreadPoolExecutor, as_completed
 from typing import Callable
 
 from SPARC import config
-
-logger = logging.getLogger(__name__)
 from SPARC.database import DatabaseClient
 from SPARC.llm import LLMAnalyzer
 from SPARC.serp_api import SERP
 from SPARC.types import BatchAnalysisResult, CompanyAnalysisResult, Patent, Patents
 
+logger = logging.getLogger(__name__)
+
 
 class CompanyAnalyzer:
     """Orchestrates end-to-end company performance analysis via patents."""

SPARC/api.py

@@ -3,9 +3,14 @@
 Provides REST API endpoints for analyzing company patent portfolios.
 """
 
+from __future__ import annotations
+
 from contextlib import asynccontextmanager
 from datetime import datetime
-from typing import Annotated, List
+from typing import TYPE_CHECKING, Annotated, List
+
+if TYPE_CHECKING:
+    from SPARC.database import DatabaseClient
 
 from fastapi import BackgroundTasks, Depends, FastAPI, HTTPException, Query, Request
 from fastapi.middleware.cors import CORSMiddleware
@@ -653,7 +658,6 @@ async def export_company_pdf(
         PDF file download
     """
     import io
-    import textwrap
 
     from reportlab.lib import colors
     from reportlab.lib.pagesizes import letter

frontend/src/pages/Analysis.tsx

@@ -159,7 +159,7 @@ export function Analysis() {
                   </button>
                 </div>
               </div>
-              <div className="prose prose-invert max-w-none">
+              <div className="prose dark:prose-invert max-w-none">
                 <div className="text-text-primary whitespace-pre-wrap leading-relaxed">
                   {result.analysis}
                 </div>

tests/test_auth.py

@@ -1,13 +1,29 @@
-"""Tests for JWT authentication flow: register, login, protected routes, refresh, admin access."""
+"""Tests for JWT authentication flow: register, login, protected routes, refresh, admin access.
 
-from datetime import datetime, timezone
+Covers all five scenarios required by issue #1624:
+1. Registration (POST /auth/register)
+2. Login (POST /auth/login)
+3. Protected route access (GET /auth/me) -- valid, missing, expired, wrong-type tokens
+4. Token refresh (POST /auth/refresh)
+5. Admin-only endpoints (GET /admin/users, PATCH role, DELETE user)
+
+All tests use mocked DB fixtures and require no live database.
+"""
+
+from datetime import datetime, timedelta, timezone
 from unittest.mock import MagicMock, patch
 
+import jwt as pyjwt
 import pytest
 from fastapi.testclient import TestClient
 
 from SPARC.api import app
-from SPARC.auth import create_access_token, create_refresh_token
+from SPARC.auth import (
+    JWT_ALGORITHM,
+    JWT_SECRET,
+    create_access_token,
+    create_refresh_token,
+)
 
 
 @pytest.fixture
@@ -171,12 +187,6 @@ class TestGetMe:
 
     def test_expired_token_returns_401(self, client, mock_db):
         """An expired token should return 401."""
-        # Create a token that has already expired
-        from datetime import timedelta
-
-        import jwt as pyjwt
-        from SPARC.auth import JWT_ALGORITHM, JWT_SECRET
-
         payload = {
             "sub": "1",
             "email": "user@test.com",
@@ -300,3 +310,193 @@ class TestAdminUsers:
 
         assert response.status_code == 400
         assert "own role" in response.json()["detail"].lower()
+
+    def test_role_change_nonexistent_user_returns_404(self, client, mock_db):
+        """Changing role for a user that does not exist should return 404."""
+        admin = _make_admin_user()
+        mock_db.get_user_by_id.return_value = admin
+        mock_db.update_user_role.return_value = None
+
+        response = client.patch(
+            "/admin/users/999/role",
+            json={"role": "admin"},
+            headers=_auth_header(admin),
+        )
+
+        assert response.status_code == 404
+        assert "not found" in response.json()["detail"].lower()
+
+    def test_regular_user_cannot_change_role(self, client, mock_db):
+        """Non-admin user should receive 403 when trying to change roles."""
+        user = _make_regular_user()
+        mock_db.get_user_by_id.return_value = user
+
+        response = client.patch(
+            "/admin/users/1/role",
+            json={"role": "admin"},
+            headers=_auth_header(user),
+        )
+
+        assert response.status_code == 403
+
+
+class TestAdminDeleteUser:
+    """DELETE /admin/users/{user_id}"""
+
+    def test_admin_can_delete_user(self, client, mock_db):
+        """Admin should be able to delete another user."""
+        admin = _make_admin_user()
+        mock_db.get_user_by_id.return_value = admin
+        mock_db.delete_user.return_value = True
+
+        response = client.delete(
+            "/admin/users/2",
+            headers=_auth_header(admin),
+        )
+
+        assert response.status_code == 200
+        assert "deleted" in response.json()["message"].lower()
+        mock_db.delete_user.assert_called_once_with(2)
+
+    def test_admin_cannot_delete_self(self, client, mock_db):
+        """Admin should not be able to delete themselves."""
+        admin = _make_admin_user()
+        mock_db.get_user_by_id.return_value = admin
+
+        response = client.delete(
+            "/admin/users/1",
+            headers=_auth_header(admin),
+        )
+
+        assert response.status_code == 400
+        assert "yourself" in response.json()["detail"].lower()
+
+    def test_delete_nonexistent_user_returns_404(self, client, mock_db):
+        """Deleting a user that does not exist should return 404."""
+        admin = _make_admin_user()
+        mock_db.get_user_by_id.return_value = admin
+        mock_db.delete_user.return_value = False
+
+        response = client.delete(
+            "/admin/users/999",
+            headers=_auth_header(admin),
+        )
+
+        assert response.status_code == 404
+        assert "not found" in response.json()["detail"].lower()
+
+    def test_regular_user_cannot_delete_user(self, client, mock_db):
+        """Non-admin user should receive 403 when trying to delete users."""
+        user = _make_regular_user()
+        mock_db.get_user_by_id.return_value = user
+
+        response = client.delete(
+            "/admin/users/1",
+            headers=_auth_header(user),
+        )
+
+        assert response.status_code == 403
+
+    def test_no_token_cannot_delete_user(self, client):
+        """Missing token should be rejected for delete endpoint."""
+        response = client.delete("/admin/users/1")
+        assert response.status_code in (401, 403)
+
+
+class TestEdgeCases:
+    """Additional edge-case tests for auth robustness."""
+
+    def test_register_invalid_email_returns_422(self, client, mock_db):
+        """Registration with an invalid email format should return 422."""
+        response = client.post(
+            "/auth/register",
+            json={"email": "not-an-email", "password": "securepass123"},
+        )
+
+        assert response.status_code == 422
+
+    def test_register_short_password_returns_422(self, client, mock_db):
+        """Registration with a password shorter than 8 chars should return 422."""
+        response = client.post(
+            "/auth/register",
+            json={"email": "user@test.com", "password": "short"},
+        )
+
+        assert response.status_code == 422
+
+    def test_register_missing_fields_returns_422(self, client, mock_db):
+        """Registration with missing fields should return 422."""
+        response = client.post("/auth/register", json={})
+        assert response.status_code == 422
+
+    def test_login_missing_fields_returns_422(self, client, mock_db):
+        """Login with missing fields should return 422."""
+        response = client.post("/auth/login", json={"email": "user@test.com"})
+        assert response.status_code == 422
+
+    def test_malformed_token_returns_401(self, client, mock_db):
+        """A completely malformed token string should return 401."""
+        response = client.get(
+            "/auth/me",
+            headers={"Authorization": "Bearer not.a.valid.jwt.token"},
+        )
+        assert response.status_code == 401
+
+    def test_token_with_wrong_secret_returns_401(self, client, mock_db):
+        """A token signed with a different secret should return 401."""
+        payload = {
+            "sub": "1",
+            "email": "user@test.com",
+            "role": "user",
+            "exp": datetime.now(timezone.utc) + timedelta(hours=1),
+            "type": "access",
+        }
+        wrong_secret_token = pyjwt.encode(payload, "wrong-secret", algorithm=JWT_ALGORITHM)
+
+        response = client.get(
+            "/auth/me",
+            headers={"Authorization": f"Bearer {wrong_secret_token}"},
+        )
+        assert response.status_code == 401
+
+    def test_token_for_deleted_user_returns_401(self, client, mock_db):
+        """A valid token for a user no longer in the DB should return 401."""
+        user = _make_regular_user()
+        mock_db.get_user_by_id.return_value = None  # user was deleted
+
+        response = client.get("/auth/me", headers=_auth_header(user))
+        assert response.status_code == 401
+
+    def test_refresh_for_deleted_user_returns_401(self, client, mock_db):
+        """Refreshing a token for a deleted user should return 401."""
+        user = _make_regular_user()
+        mock_db.get_user_by_id.return_value = None
+        refresh = create_refresh_token(user["id"], user["email"], user["role"])
+
+        response = client.post(
+            "/auth/refresh", json={"refresh_token": refresh}
+        )
+        assert response.status_code == 401
+
+    def test_login_returns_decodable_tokens(self, client, mock_db):
+        """Tokens returned by login should be decodable and contain expected claims."""
+        user = _make_regular_user()
+        mock_db.authenticate_user.return_value = user
+
+        response = client.post(
+            "/auth/login",
+            json={"email": "user@test.com", "password": "correctpassword"},
+        )
+
+        data = response.json()
+        access_payload = pyjwt.decode(
+            data["access_token"], JWT_SECRET, algorithms=[JWT_ALGORITHM]
+        )
+        assert access_payload["sub"] == str(user["id"])
+        assert access_payload["email"] == user["email"]
+        assert access_payload["type"] == "access"
+
+        refresh_payload = pyjwt.decode(
+            data["refresh_token"], JWT_SECRET, algorithms=[JWT_ALGORITHM]
+        )
+        assert refresh_payload["type"] == "refresh"

tests/test_rate_limit.py

@@ -1,7 +1,8 @@
 """Tests for rate limiting on auth endpoints."""
 
+from unittest.mock import MagicMock, patch
+
 import pytest
-from unittest.mock import Mock, patch, MagicMock
 from fastapi.testclient import TestClient
 
 from SPARC.api import app

tests/test_security.py

@@ -14,6 +14,7 @@ class TestJWTSecretStartupCheck:
         with patch.dict(os.environ, {"APP_ENV": "production"}):
             # Reload config to pick up the new APP_ENV
             import importlib
+
             import SPARC.config
             importlib.reload(SPARC.config)
 
@@ -31,6 +32,7 @@ class TestJWTSecretStartupCheck:
         """Starting with default secret and APP_ENV=development must not raise."""
         with patch.dict(os.environ, {"APP_ENV": "development"}):
             import importlib
+
             import SPARC.config
             importlib.reload(SPARC.config)
 
@@ -46,6 +48,7 @@ class TestJWTSecretStartupCheck:
         """Starting with a custom secret in production must not raise."""
         with patch.dict(os.environ, {"APP_ENV": "production"}):
             import importlib
+
             import SPARC.config
             importlib.reload(SPARC.config)
 
@@ -65,6 +68,7 @@ class TestJWTSecretStartupCheck:
             env.pop("APP_ENV", None)
             with patch.dict(os.environ, env, clear=True):
                 import importlib
+
                 import SPARC.config
                 importlib.reload(SPARC.config)
 
@@ -84,6 +88,7 @@ class TestCORSConfig:
         """When CORS_ORIGINS is unset, defaults to localhost origins."""
         with patch.dict(os.environ, {"CORS_ORIGINS": ""}):
             import importlib
+
             import SPARC.config
             importlib.reload(SPARC.config)
             assert SPARC.config.cors_origins == [
@@ -95,6 +100,7 @@ class TestCORSConfig:
         """Setting CORS_ORIGINS configures allowed origins."""
         with patch.dict(os.environ, {"CORS_ORIGINS": "https://sparc.example.com,https://app.example.com"}):
             import importlib
+
             import SPARC.config
             importlib.reload(SPARC.config)
             assert SPARC.config.cors_origins == [
@@ -109,6 +115,7 @@ class TestCORSConfig:
         """A single origin without comma works correctly."""
         with patch.dict(os.environ, {"CORS_ORIGINS": "https://sparc.example.com"}):
             import importlib
+
             import SPARC.config
             importlib.reload(SPARC.config)
             assert SPARC.config.cors_origins == ["https://sparc.example.com"]

tests/test_storage.py

@@ -0,0 +1,263 @@
+"""Tests for S3/MinIO storage backend in storage.py.
+
+Covers issue #1660:
+- S3StorageBackend read, write, exists, path_for
+- Error handling: NoSuchKey, generic S3 errors, bucket auto-creation
+- get_storage_backend() factory function
+- LocalStorageBackend (basic sanity checks)
+"""
+
+from unittest.mock import MagicMock, patch
+
+import pytest
+
+from SPARC.storage import LocalStorageBackend, S3StorageBackend, get_storage_backend
+
+
+# ---------- S3StorageBackend ----------
+
+class TestS3StorageBackend:
+    """Tests for the S3-compatible storage backend."""
+
+    @pytest.fixture
+    def s3_backend(self):
+        """Create an S3StorageBackend with a fully mocked boto3 client."""
+        with patch.dict("sys.modules", {"boto3": MagicMock()}):
+            import boto3 as mock_boto
+            mock_s3 = MagicMock()
+            mock_boto.client.return_value = mock_s3
+            mock_s3.head_bucket.return_value = {}
+
+            backend = S3StorageBackend(
+                bucket="test-bucket",
+                endpoint_url="http://minio:9000",
+                access_key="minioadmin",
+                secret_key="minioadmin",
+            )
+            # Expose mock for assertions
+            backend._mock_s3 = mock_s3
+            yield backend
+
+    def test_write_puts_object(self, s3_backend):
+        """write() calls put_object with correct bucket, key, and body."""
+        s3_backend.write("US-12345678-B2.pdf", b"PDF content here")
+
+        s3_backend._mock_s3.put_object.assert_called_once_with(
+            Bucket="test-bucket",
+            Key="US-12345678-B2.pdf",
+            Body=b"PDF content here",
+            ContentType="application/pdf",
+        )
+
+    def test_read_returns_body(self, s3_backend):
+        """read() returns the Body content from get_object."""
+        mock_body = MagicMock()
+        mock_body.read.return_value = b"PDF data"
+        s3_backend._mock_s3.get_object.return_value = {"Body": mock_body}
+
+        result = s3_backend.read("US-12345678-B2.pdf")
+
+        assert result == b"PDF data"
+        s3_backend._mock_s3.get_object.assert_called_once_with(
+            Bucket="test-bucket",
+            Key="US-12345678-B2.pdf",
+        )
+
+    def test_read_nosuchkey_raises_file_not_found(self, s3_backend):
+        """read() raises FileNotFoundError when object does not exist."""
+        # Create a NoSuchKey exception class on the mock
+        nosuchkey = type("NoSuchKey", (Exception,), {})
+        s3_backend._mock_s3.exceptions.NoSuchKey = nosuchkey
+        s3_backend._mock_s3.get_object.side_effect = nosuchkey("not found")
+
+        # Reassign s3 to trigger the except branch
+        s3_backend.s3 = s3_backend._mock_s3
+
+        with pytest.raises(FileNotFoundError, match="S3 object not found"):
+            s3_backend.read("missing.pdf")
+
+    def test_read_generic_404_raises_file_not_found(self, s3_backend):
+        """read() handles generic 404 errors from S3-compatible APIs."""
+        nosuchkey = type("NoSuchKey", (Exception,), {})
+        s3_backend._mock_s3.exceptions.NoSuchKey = nosuchkey
+        s3_backend.s3 = s3_backend._mock_s3
+        s3_backend.s3.get_object.side_effect = Exception("An error occurred (404)")
+
+        with pytest.raises(FileNotFoundError, match="S3 object not found"):
+            s3_backend.read("missing.pdf")
+
+    def test_read_other_error_re_raises(self, s3_backend):
+        """read() re-raises non-404 errors."""
+        nosuchkey = type("NoSuchKey", (Exception,), {})
+        s3_backend._mock_s3.exceptions.NoSuchKey = nosuchkey
+        s3_backend.s3 = s3_backend._mock_s3
+        s3_backend.s3.get_object.side_effect = Exception("Internal server error")
+
+        with pytest.raises(Exception, match="Internal server error"):
+            s3_backend.read("some-file.pdf")
+
+    def test_exists_returns_true_for_existing_object(self, s3_backend):
+        """exists() returns True when head_object succeeds with content."""
+        s3_backend._mock_s3.head_object.return_value = {"ContentLength": 1024}
+
+        assert s3_backend.exists("US-12345678-B2.pdf") is True
+
+    def test_exists_returns_false_for_missing_object(self, s3_backend):
+        """exists() returns False when head_object raises an exception."""
+        s3_backend._mock_s3.head_object.side_effect = Exception("Not Found")
+
+        assert s3_backend.exists("missing.pdf") is False
+
+    def test_exists_returns_false_for_zero_length(self, s3_backend):
+        """exists() returns False when object has zero content length."""
+        s3_backend._mock_s3.head_object.return_value = {"ContentLength": 0}
+
+        assert s3_backend.exists("empty.pdf") is False
+
+    def test_path_for_returns_s3_uri(self, s3_backend):
+        """path_for() returns an s3:// URI."""
+        path = s3_backend.path_for("US-12345678-B2.pdf")
+
+        assert path == "s3://test-bucket/US-12345678-B2.pdf"
+
+    def test_constructor_creates_bucket_if_missing(self):
+        """Constructor creates the bucket if head_bucket fails."""
+        with patch.dict("sys.modules", {"boto3": MagicMock()}):
+            import boto3 as mock_boto
+            mock_s3 = MagicMock()
+            mock_boto.client.return_value = mock_s3
+            mock_s3.head_bucket.side_effect = Exception("Bucket not found")
+
+            S3StorageBackend(
+                bucket="new-bucket",
+                endpoint_url="http://minio:9000",
+                access_key="admin",
+                secret_key="admin",
+            )
+
+            mock_s3.create_bucket.assert_called_once_with(Bucket="new-bucket")
+
+    def test_constructor_handles_bucket_creation_failure(self):
+        """Constructor logs warning but does not crash if bucket creation fails."""
+        with patch.dict("sys.modules", {"boto3": MagicMock()}):
+            import boto3 as mock_boto
+            mock_s3 = MagicMock()
+            mock_boto.client.return_value = mock_s3
+            mock_s3.head_bucket.side_effect = Exception("Bucket not found")
+            mock_s3.create_bucket.side_effect = Exception("Permission denied")
+
+            # Should not raise
+            backend = S3StorageBackend(
+                bucket="locked-bucket",
+                endpoint_url="http://minio:9000",
+                access_key="admin",
+                secret_key="admin",
+            )
+            assert backend.bucket == "locked-bucket"
+
+    def test_constructor_passes_endpoint_and_credentials(self):
+        """Constructor passes endpoint_url and credentials to boto3.client."""
+        with patch.dict("sys.modules", {"boto3": MagicMock()}):
+            import boto3 as mock_boto
+            mock_s3 = MagicMock()
+            mock_boto.client.return_value = mock_s3
+
+            S3StorageBackend(
+                bucket="test",
+                endpoint_url="http://minio:9000",
+                access_key="mykey",
+                secret_key="mysecret",
+            )
+
+            mock_boto.client.assert_called_with(
+                "s3",
+                endpoint_url="http://minio:9000",
+                aws_access_key_id="mykey",
+                aws_secret_access_key="mysecret",
+            )
+
+
+# ---------- LocalStorageBackend ----------
+
+class TestLocalStorageBackend:
+    """Basic sanity checks for the local filesystem backend."""
+
+    def test_write_and_read(self, tmp_path):
+        """Write and read round-trip produces identical content."""
+        backend = LocalStorageBackend(base_dir=str(tmp_path))
+        backend.write("test.pdf", b"hello world")
+
+        result = backend.read("test.pdf")
+        assert result == b"hello world"
+
+    def test_read_missing_file_raises(self, tmp_path):
+        """Reading a non-existent file raises FileNotFoundError."""
+        backend = LocalStorageBackend(base_dir=str(tmp_path))
+
+        with pytest.raises(FileNotFoundError):
+            backend.read("nonexistent.pdf")
+
+    def test_exists_true_for_written_file(self, tmp_path):
+        """exists() returns True after writing a file."""
+        backend = LocalStorageBackend(base_dir=str(tmp_path))
+        backend.write("test.pdf", b"data")
+
+        assert backend.exists("test.pdf") is True
+
+    def test_exists_false_for_missing_file(self, tmp_path):
+        """exists() returns False for non-existent file."""
+        backend = LocalStorageBackend(base_dir=str(tmp_path))
+
+        assert backend.exists("missing.pdf") is False
+
+    def test_exists_false_for_empty_file(self, tmp_path):
+        """exists() returns False for zero-length file."""
+        backend = LocalStorageBackend(base_dir=str(tmp_path))
+        backend.write("empty.pdf", b"")
+
+        assert backend.exists("empty.pdf") is False
+
+    def test_path_for_returns_full_path(self, tmp_path):
+        """path_for() returns the full filesystem path."""
+        backend = LocalStorageBackend(base_dir=str(tmp_path))
+        path = backend.path_for("test.pdf")
+
+        assert path == str(tmp_path / "test.pdf")
+
+
+# ---------- get_storage_backend() factory ----------
+
+class TestGetStorageBackend:
+    """Tests for the storage backend factory function."""
+
+    @patch("SPARC.storage.config")
+    def test_returns_local_backend_by_default(self, mock_config):
+        """Default config returns LocalStorageBackend."""
+        mock_config.storage_backend = "local"
+
+        backend = get_storage_backend()
+
+        assert isinstance(backend, LocalStorageBackend)
+
+    @patch("SPARC.storage.config")
+    def test_returns_s3_backend_when_configured(self, mock_config):
+        """Setting storage_backend=s3 returns S3StorageBackend."""
+        mock_config.storage_backend = "s3"
+        mock_config.s3_bucket = "test-bucket"
+        mock_config.s3_endpoint_url = "http://minio:9000"
+        mock_config.s3_access_key = "key"
+        mock_config.s3_secret_key = "secret"
+
+        with patch.dict("sys.modules", {"boto3": MagicMock()}):
+            backend = get_storage_backend()
+
+        assert isinstance(backend, S3StorageBackend)
+
+    @patch("SPARC.storage.config")
+    def test_case_insensitive_backend_selection(self, mock_config):
+        """Backend selection is case-insensitive."""
+        mock_config.storage_backend = "LOCAL"
+
+        backend = get_storage_backend()
+
+        assert isinstance(backend, LocalStorageBackend)